相关论文: Gradient Surgery for Safe LLM Fine-Tuning

Recent studies have uncovered a troubling vulnerability in the fine-tuning stage of large language models (LLMs): even fine-tuning on entirely benign datasets can lead to a significant increase in the harmfulness of LLM outputs. Building on…

Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse…

The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation…

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

The advent of large language models (LLMs) in the education sector has provided impetus to automate grading short answer questions. LLMs make evaluating short answers very efficient, thus addressing issues like staff shortage. However, in…

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

With the recent proliferation of large language models (LLMs), enterprises have been able to rapidly develop proof-of-concepts and prototypes. As a result, there is a growing need to implement robust guardrails that monitor, quantize and…

Most prior safety research of large language models (LLMs) has focused on enhancing the alignment of LLMs to better suit the safety requirements of humans. However, internalizing such safeguard features into larger models brought challenges…

Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: safety alignment methods designed to filter harmful content…

Safe Reinforcement Learning (Safe RL) is one of the prevalently studied subcategories of trial-and-error-based methods with the intention to be deployed on real-world systems. In safe RL, the goal is to maximize reward performance while…

Large language models (LLMs) have shown great potential as general-purpose AI assistants in various domains. To meet the requirements of different applications, LLMs are often customized by further fine-tuning. However, the powerful…

Software security vulnerabilities allow attackers to perform malicious activities to disrupt software operations. Recent Transformer-based language models have significantly advanced vulnerability detection, surpassing the capabilities of…

The emergence of vision language models (VLMs) comes with increased safety concerns, as the incorporation of multiple modalities heightens vulnerability to attacks. Although VLMs can be built upon LLMs that have textual safety alignment, it…

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

Recent studies show that the safety alignment of large language models (LLMs) can be easily compromised even by seemingly non-adversarial fine-tuning. To preserve safety alignment during fine-tuning, a widely used strategy is to jointly…

This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function…

Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief…

Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, both approaches have…

Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs) into Large Vision-Language Models (LVLMs) for multimodal tasks, but this process often compromises the inherent safety capabilities embedded in the original…